From: Junaid Shahid <junaids@google.com>
To: linux-kernel@vger.kernel.org
Cc: kvm@vger.kernel.org, pbonzini@redhat.com, jmattson@google.com,
pjt@google.com, oweisse@google.com, alexandre.chartre@oracle.com,
rppt@linux.ibm.com, dave.hansen@linux.intel.com,
peterz@infradead.org, tglx@linutronix.de, luto@kernel.org,
linux-mm@kvack.org
Subject: [RFC PATCH 32/47] x86: asi: Allocate FPU state separately when ASI is enabled.
Date: Tue, 22 Feb 2022 21:22:08 -0800 [thread overview]
Message-ID: <20220223052223.1202152-33-junaids@google.com> (raw)
In-Reply-To: <20220223052223.1202152-1-junaids@google.com>
We are going to be mapping the task_struct in the restricted ASI
address space. However, the task_struct also contains the FPU
register state embedded inside it, which can contain sensitive
information. So when ASI is enabled, always allocate the FPU
state from a separate slab cache to keep it out of task_struct.
Signed-off-by: Junaid Shahid <junaids@google.com>
---
arch/x86/include/asm/fpu/api.h | 1 +
arch/x86/kernel/fpu/core.c | 45 ++++++++++++++++++++++++++++++++--
arch/x86/kernel/fpu/init.c | 7 ++++--
arch/x86/kernel/fpu/internal.h | 1 +
arch/x86/kernel/fpu/xstate.c | 21 +++++++++++++---
arch/x86/kernel/process.c | 7 +++++-
6 files changed, 74 insertions(+), 8 deletions(-)
diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h
index c2767a6a387e..6f5ca3c2ef4a 100644
--- a/arch/x86/include/asm/fpu/api.h
+++ b/arch/x86/include/asm/fpu/api.h
@@ -112,6 +112,7 @@ extern void fpu__init_cpu(void);
extern void fpu__init_system(struct cpuinfo_x86 *c);
extern void fpu__init_check_bugs(void);
extern void fpu__resume_cpu(void);
+extern void fpstate_cache_init(void);
#ifdef CONFIG_MATH_EMULATION
extern void fpstate_init_soft(struct swregs_state *soft);
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 8ea306b1bf8e..d7859573973d 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -59,6 +59,8 @@ static DEFINE_PER_CPU(bool, in_kernel_fpu);
*/
DEFINE_PER_CPU(struct fpu *, fpu_fpregs_owner_ctx);
+struct kmem_cache *fpstate_cachep;
+
static bool kernel_fpu_disabled(void)
{
return this_cpu_read(in_kernel_fpu);
@@ -443,7 +445,9 @@ static void __fpstate_reset(struct fpstate *fpstate)
void fpstate_reset(struct fpu *fpu)
{
/* Set the fpstate pointer to the default fpstate */
- fpu->fpstate = &fpu->__fpstate;
+ if (!cpu_feature_enabled(X86_FEATURE_ASI))
+ fpu->fpstate = &fpu->__fpstate;
+
__fpstate_reset(fpu->fpstate);
/* Initialize the permission related info in fpu */
@@ -464,6 +468,26 @@ static inline void fpu_inherit_perms(struct fpu *dst_fpu)
}
}
+void fpstate_cache_init(void)
+{
+ if (cpu_feature_enabled(X86_FEATURE_ASI)) {
+ size_t fpstate_size;
+
+ /* TODO: Is the ALIGN-64 really needed? */
+ fpstate_size = fpu_kernel_cfg.default_size +
+ ALIGN(offsetof(struct fpstate, regs), 64);
+
+ fpstate_cachep = kmem_cache_create_usercopy(
+ "fpstate",
+ fpstate_size,
+ __alignof__(struct fpstate),
+ SLAB_PANIC | SLAB_ACCOUNT,
+ offsetof(struct fpstate, regs),
+ fpu_kernel_cfg.default_size,
+ NULL);
+ }
+}
+
/* Clone current's FPU state on fork */
int fpu_clone(struct task_struct *dst, unsigned long clone_flags)
{
@@ -473,6 +497,22 @@ int fpu_clone(struct task_struct *dst, unsigned long clone_flags)
/* The new task's FPU state cannot be valid in the hardware. */
dst_fpu->last_cpu = -1;
+ if (cpu_feature_enabled(X86_FEATURE_ASI)) {
+ dst_fpu->fpstate = kmem_cache_alloc_node(
+ fpstate_cachep, GFP_KERNEL,
+ page_to_nid(virt_to_page(dst)));
+ if (!dst_fpu->fpstate)
+ return -ENOMEM;
+
+ /*
+ * TODO: We may be able to skip the copy since the registers are
+ * restored below anyway.
+ */
+ memcpy(dst_fpu->fpstate, src_fpu->fpstate,
+ fpu_kernel_cfg.default_size +
+ offsetof(struct fpstate, regs));
+ }
+
fpstate_reset(dst_fpu);
if (!cpu_feature_enabled(X86_FEATURE_FPU))
@@ -531,7 +571,8 @@ int fpu_clone(struct task_struct *dst, unsigned long clone_flags)
void fpu_thread_struct_whitelist(unsigned long *offset, unsigned long *size)
{
*offset = offsetof(struct thread_struct, fpu.__fpstate.regs);
- *size = fpu_kernel_cfg.default_size;
+ *size = cpu_feature_enabled(X86_FEATURE_ASI)
+ ? 0 : fpu_kernel_cfg.default_size;
}
/*
diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
index 621f4b6cac4a..8b722bf98135 100644
--- a/arch/x86/kernel/fpu/init.c
+++ b/arch/x86/kernel/fpu/init.c
@@ -161,9 +161,11 @@ static void __init fpu__init_task_struct_size(void)
/*
* Add back the dynamically-calculated register state
- * size.
+ * size, except when ASI is enabled, since in that case
+ * the FPU state is always allocated dynamically.
*/
- task_size += fpu_kernel_cfg.default_size;
+ if (!cpu_feature_enabled(X86_FEATURE_ASI))
+ task_size += fpu_kernel_cfg.default_size;
/*
* We dynamically size 'struct fpu', so we require that
@@ -223,6 +225,7 @@ static void __init fpu__init_init_fpstate(void)
*/
void __init fpu__init_system(struct cpuinfo_x86 *c)
{
+ current->thread.fpu.fpstate = ¤t->thread.fpu.__fpstate;
fpstate_reset(¤t->thread.fpu);
fpu__init_system_early_generic(c);
diff --git a/arch/x86/kernel/fpu/internal.h b/arch/x86/kernel/fpu/internal.h
index dbdb31f55fc7..30acc7d0cb1a 100644
--- a/arch/x86/kernel/fpu/internal.h
+++ b/arch/x86/kernel/fpu/internal.h
@@ -3,6 +3,7 @@
#define __X86_KERNEL_FPU_INTERNAL_H
extern struct fpstate init_fpstate;
+extern struct kmem_cache *fpstate_cachep;
/* CPU feature check wrappers */
static __always_inline __pure bool use_xsave(void)
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index d28829403ed0..96d12f351f19 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -13,6 +13,7 @@
#include <linux/seq_file.h>
#include <linux/proc_fs.h>
#include <linux/vmalloc.h>
+#include <linux/slab.h>
#include <asm/fpu/api.h>
#include <asm/fpu/regset.h>
@@ -1495,8 +1496,15 @@ arch_initcall(xfd_update_static_branch)
void fpstate_free(struct fpu *fpu)
{
- if (fpu->fpstate && fpu->fpstate != &fpu->__fpstate)
- vfree(fpu->fpstate);
+ WARN_ON_ONCE(cpu_feature_enabled(X86_FEATURE_ASI) &&
+ fpu->fpstate == &fpu->__fpstate);
+
+ if (fpu->fpstate && fpu->fpstate != &fpu->__fpstate) {
+ if (fpu->fpstate->is_valloc)
+ vfree(fpu->fpstate);
+ else
+ kmem_cache_free(fpstate_cachep, fpu->fpstate);
+ }
}
/**
@@ -1574,7 +1582,14 @@ static int fpstate_realloc(u64 xfeatures, unsigned int ksize,
fpregs_unlock();
- vfree(curfps);
+ WARN_ON_ONCE(cpu_feature_enabled(X86_FEATURE_ASI) && !curfps);
+ if (curfps) {
+ if (curfps->is_valloc)
+ vfree(curfps);
+ else
+ kmem_cache_free(fpstate_cachep, curfps);
+ }
+
return 0;
}
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index c8d4a00a4de7..f9bd1c3415d4 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -80,6 +80,11 @@ EXPORT_PER_CPU_SYMBOL(cpu_tss_rw);
DEFINE_PER_CPU(bool, __tss_limit_invalid);
EXPORT_PER_CPU_SYMBOL_GPL(__tss_limit_invalid);
+void __init arch_task_cache_init(void)
+{
+ fpstate_cache_init();
+}
+
/*
* this gets called so that we can store lazy state into memory and copy the
* current task into the new thread.
@@ -101,7 +106,7 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
#ifdef CONFIG_X86_64
void arch_release_task_struct(struct task_struct *tsk)
{
- if (fpu_state_size_dynamic())
+ if (fpu_state_size_dynamic() || cpu_feature_enabled(X86_FEATURE_ASI))
fpstate_free(&tsk->thread.fpu);
}
#endif
--
2.35.1.473.g83b2b277ed-goog
next prev parent reply other threads:[~2022-02-23 5:28 UTC|newest]
Thread overview: 64+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-02-23 5:21 [RFC PATCH 00/47] Address Space Isolation for KVM Junaid Shahid
2022-02-23 5:21 ` [RFC PATCH 01/47] mm: asi: Introduce ASI core API Junaid Shahid
2022-02-23 5:21 ` [RFC PATCH 02/47] mm: asi: Add command-line parameter to enable/disable ASI Junaid Shahid
2022-02-23 5:21 ` [RFC PATCH 03/47] mm: asi: Switch to unrestricted address space when entering scheduler Junaid Shahid
2022-02-23 5:21 ` [RFC PATCH 04/47] mm: asi: ASI support in interrupts/exceptions Junaid Shahid
2022-03-14 15:50 ` Thomas Gleixner
2022-03-15 2:01 ` Junaid Shahid
2022-03-15 12:55 ` Thomas Gleixner
2022-03-15 22:41 ` Junaid Shahid
2022-02-23 5:21 ` [RFC PATCH 05/47] mm: asi: Make __get_current_cr3_fast() ASI-aware Junaid Shahid
2022-02-23 5:21 ` [RFC PATCH 06/47] mm: asi: ASI page table allocation and free functions Junaid Shahid
2022-02-23 5:21 ` [RFC PATCH 07/47] mm: asi: Functions to map/unmap a memory range into ASI page tables Junaid Shahid
2022-02-23 5:21 ` [RFC PATCH 08/47] mm: asi: Add basic infrastructure for global non-sensitive mappings Junaid Shahid
2022-02-23 5:21 ` [RFC PATCH 09/47] mm: Add __PAGEFLAG_FALSE Junaid Shahid
2022-02-23 5:21 ` [RFC PATCH 10/47] mm: asi: Support for global non-sensitive direct map allocations Junaid Shahid
2022-03-23 21:06 ` Matthew Wilcox
2022-03-23 23:48 ` Junaid Shahid
2022-03-24 1:54 ` Junaid Shahid
2022-02-23 5:21 ` [RFC PATCH 11/47] mm: asi: Global non-sensitive vmalloc/vmap support Junaid Shahid
2022-02-23 5:21 ` [RFC PATCH 12/47] mm: asi: Support for global non-sensitive slab caches Junaid Shahid
2022-02-23 5:21 ` [RFC PATCH 13/47] asi: Added ASI memory cgroup flag Junaid Shahid
2022-02-23 5:21 ` [RFC PATCH 14/47] mm: asi: Disable ASI API when ASI is not enabled for a process Junaid Shahid
2022-02-23 5:21 ` [RFC PATCH 15/47] kvm: asi: Restricted address space for VM execution Junaid Shahid
2022-02-23 5:21 ` [RFC PATCH 16/47] mm: asi: Support for mapping non-sensitive pcpu chunks Junaid Shahid
2022-02-23 5:21 ` [RFC PATCH 17/47] mm: asi: Aliased direct map for local non-sensitive allocations Junaid Shahid
2022-02-23 5:21 ` [RFC PATCH 18/47] mm: asi: Support for pre-ASI-init " Junaid Shahid
2022-02-23 5:21 ` [RFC PATCH 19/47] mm: asi: Support for locally nonsensitive page allocations Junaid Shahid
2022-02-23 5:21 ` [RFC PATCH 20/47] mm: asi: Support for locally non-sensitive vmalloc allocations Junaid Shahid
2022-02-23 5:21 ` [RFC PATCH 21/47] mm: asi: Add support for locally non-sensitive VM_USERMAP pages Junaid Shahid
2022-02-23 5:21 ` [RFC PATCH 22/47] mm: asi: Added refcounting when initilizing an asi Junaid Shahid
2022-02-23 5:21 ` [RFC PATCH 23/47] mm: asi: Add support for mapping all userspace memory into ASI Junaid Shahid
2022-02-23 5:22 ` [RFC PATCH 24/47] mm: asi: Support for local non-sensitive slab caches Junaid Shahid
2022-02-23 5:22 ` [RFC PATCH 25/47] mm: asi: Avoid warning from NMI userspace accesses in ASI context Junaid Shahid
2022-02-23 5:22 ` [RFC PATCH 26/47] mm: asi: Use separate PCIDs for restricted address spaces Junaid Shahid
2022-02-23 5:22 ` [RFC PATCH 27/47] mm: asi: Avoid TLB flushes during ASI CR3 switches when possible Junaid Shahid
2022-02-23 5:22 ` [RFC PATCH 28/47] mm: asi: Avoid TLB flush IPIs to CPUs not in ASI context Junaid Shahid
2022-02-23 5:22 ` [RFC PATCH 29/47] mm: asi: Reduce TLB flushes when freeing pages asynchronously Junaid Shahid
2022-02-23 5:22 ` [RFC PATCH 30/47] mm: asi: Add API for mapping userspace address ranges Junaid Shahid
2022-02-23 5:22 ` [RFC PATCH 31/47] mm: asi: Support for non-sensitive SLUB caches Junaid Shahid
2022-02-23 5:22 ` Junaid Shahid [this message]
2022-02-23 5:22 ` [RFC PATCH 33/47] kvm: asi: Map guest memory into restricted ASI address space Junaid Shahid
2022-02-23 5:22 ` [RFC PATCH 34/47] kvm: asi: Unmap guest memory from ASI address space when using nested virt Junaid Shahid
2022-02-23 5:22 ` [RFC PATCH 35/47] mm: asi: asi_exit() on PF, skip handling if address is accessible Junaid Shahid
2022-02-23 5:22 ` [RFC PATCH 36/47] mm: asi: Adding support for dynamic percpu ASI allocations Junaid Shahid
2022-02-23 5:22 ` [RFC PATCH 37/47] mm: asi: ASI annotation support for static variables Junaid Shahid
2022-02-23 5:22 ` [RFC PATCH 38/47] mm: asi: ASI annotation support for dynamic modules Junaid Shahid
2022-02-23 5:22 ` [RFC PATCH 39/47] mm: asi: Skip conventional L1TF/MDS mitigations Junaid Shahid
2022-02-23 5:22 ` [RFC PATCH 40/47] mm: asi: support for static percpu DEFINE_PER_CPU*_ASI Junaid Shahid
2022-02-23 5:22 ` [RFC PATCH 41/47] mm: asi: Annotation of static variables to be nonsensitive Junaid Shahid
2022-02-23 5:22 ` [RFC PATCH 42/47] mm: asi: Annotation of PERCPU " Junaid Shahid
2022-02-23 5:22 ` [RFC PATCH 43/47] mm: asi: Annotation of dynamic " Junaid Shahid
2022-02-23 5:22 ` [RFC PATCH 44/47] kvm: asi: Splitting kvm_vcpu_arch into non/sensitive parts Junaid Shahid
2022-02-23 5:22 ` [RFC PATCH 45/47] mm: asi: Mapping global nonsensitive areas in asi_global_init Junaid Shahid
2022-02-23 5:22 ` [RFC PATCH 46/47] kvm: asi: Do asi_exit() in vcpu_run loop before returning to userspace Junaid Shahid
2022-02-23 5:22 ` [RFC PATCH 47/47] mm: asi: Properly un/mapping task stack from ASI + tlb flush Junaid Shahid
2022-03-05 3:39 ` [RFC PATCH 00/47] Address Space Isolation for KVM Hyeonggon Yoo
2022-03-16 21:34 ` Alexandre Chartre
2022-03-17 23:25 ` Junaid Shahid
2022-03-22 9:46 ` Alexandre Chartre
2022-03-23 19:35 ` Junaid Shahid
2022-04-08 8:52 ` Alexandre Chartre
2022-04-11 3:26 ` junaid_shahid
2022-03-16 22:49 ` Thomas Gleixner
2022-03-17 21:24 ` Junaid Shahid
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20220223052223.1202152-33-junaids@google.com \
--to=junaids@google.com \
--cc=alexandre.chartre@oracle.com \
--cc=dave.hansen@linux.intel.com \
--cc=jmattson@google.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=luto@kernel.org \
--cc=oweisse@google.com \
--cc=pbonzini@redhat.com \
--cc=peterz@infradead.org \
--cc=pjt@google.com \
--cc=rppt@linux.ibm.com \
--cc=tglx@linutronix.de \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.